clawhub

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

3.84x

Quality

87%

Does it follow best practices?

Impact

100%

3.84x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is clawhub in Hung-Reo/hungreo-openclaw

Quality

Content

87%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary lean, fully executable CLI reference with perfect token efficiency and organization. Its one weakness is the absence of validation/verification guidance around batch and destructive operations (update --all --force, publish), which the rubric caps at 3 for workflow clarity.

Suggestions

Add a verification step for batch updates, e.g. after "clawhub update --all --force", run "clawhub list" to confirm installed versions and roll back with "clawhub install <skill> --version <previous>" if an upgrade breaks a skill.

Add a pre-publish checklist (e.g. confirm "clawhub whoami" succeeds and review the changelog/version bump) so the destructive publish step validates before overwriting registry state.

Briefly note what "hash-based match" means operationally during update (what happens when a local skill has no matching remote version), since that failure path is currently undocumented.

Dimension	Reasoning	Score
Conciseness	Lean command-per-section reference with zero over-explanation: "Install", "Auth (publish)", "Search", "Update", "Publish", and a short Notes list. Every token earns its place and nothing explains concepts Claude already knows.	5 / 5
Actionability	Fully executable copy-paste commands covering common cases, including flag variants ("clawhub install my-skill --version 1.2.3", "clawhub update --all --no-input --force", a complete publish invocation with --slug/--name/--version/--changelog). Not level 4 because there are no gaps: the examples cover the common cases for every subcommand shown.	5 / 5
Workflow Clarity	Sections are labeled and commands sequenced per task, but batch/destructive operations ("clawhub update --all --force", "clawhub publish") have no validation or verification steps — e.g. running "clawhub list" after update or confirming the published version. Per the rubric, missing validation on destructive/batch operations caps workflow clarity at 3 even for a single-purpose skill; it is not 2 because the sequence and commands themselves are clear and unambiguous.	3 / 5
Progressive Disclosure	A short (~30 content lines), single-purpose reference with well-organized labeled sections and no external bundle files needed; no references exist in references/, scripts/, or assets/, so the inline-only structure is appropriate for this size, matching the simple-skill 5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that states concrete capabilities and an explicit trigger clause covering all three use modes (fetch, sync, publish). The only deduction is the second-person "you need" phrasing, which the rubric penalizes on specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (ClawHub CLI, clawhub.com) and multiple concrete actions — "search, install, update, and publish agent skills" — with comprehensive coverage of the CLI's operation surface. The second-person phrasing "Use when you need to fetch new skills on the fly" triggers the rubric's one-point specificity penalty from an otherwise level-5 description.	4 / 5
Completeness	Explicitly answers both: what ("search, install, update, and publish agent skills from clawhub.com") and when ("Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders"), with concrete trigger phrases matching the level-5 anchor.	5 / 5
Trigger Term Quality	Good natural-phrase coverage: "fetch new skills on the fly", "sync installed skills to latest or a specific version", "publish new/updated skill folders", plus product terms (ClawHub, clawhub.com, npm). A few natural variants users might say (e.g. "find a skill", "browse the marketplace", "list installed skills") are absent, keeping it below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche: a named product (ClawHub CLI / clawhub.com) with distinct triggers around skill fetching, syncing, and publishing; minimal overlap risk with generic package-manager or skill-management skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: trpc-group/trpc-agent-go
Path: openclaw/skills/clawhub/SKILL.md
Commit: 9bb1c42

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.